linux-kernel - Re: [PATCH 4/4] sched: Idle task shortcut optimization

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20140117140939.GH11314@laptop.programming.kicks-ass.net>
Date:	Fri, 17 Jan 2014 15:09:39 +0100
From:	Peter Zijlstra <peterz@...radead.org>
To:	Daniel Lezcano <daniel.lezcano@...aro.org>
Cc:	mingo@...nel.org, linux-kernel@...r.kernel.org,
	linaro-kernel@...ts.linaro.org, alex.shi@...aro.org
Subject: Re: [PATCH 4/4] sched: Idle task shortcut optimization

On Fri, Jan 17, 2014 at 10:04:04AM +0100, Daniel Lezcano wrote:
> +	schedstat_inc(rq, sched_goidle);
> +#ifdef CONFIG_SMP
> +	/* Trigger the post schedule to do an idle_enter for CFS */
> +	rq->post_schedule = 1;
> +#endif
> +	return rq->idle;

Urgh, that retains the stupid idle crap like it is.

I've not yet tested this, but is there a reason something like the below
couldn't work?

---
Subject: sched: Clean up idle task SMP logic
From: Peter Zijlstra <peterz@...radead.org>
Date: Fri Jan 17 14:54:02 CET 2014

The idle post_schedule hook is just a vile waste of time, fix it proper.

Signed-off-by: Peter Zijlstra <peterz@...radead.org>
---
 kernel/sched/fair.c      |    5 +++--
 kernel/sched/idle_task.c |   21 ++++++---------------
 2 files changed, 9 insertions(+), 17 deletions(-)

Index: linux-2.6/kernel/sched/fair.c
===================================================================
--- linux-2.6.orig/kernel/sched/fair.c
+++ linux-2.6/kernel/sched/fair.c
@@ -2416,7 +2416,8 @@ void idle_exit_fair(struct rq *this_rq)
 	update_rq_runnable_avg(this_rq, 0);
 }
 
-#else
+#else /* CONFIG_SMP */
+
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
@@ -2428,7 +2429,7 @@ static inline void dequeue_entity_load_a
 					   int sleep) {}
 static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
 					      int force_update) {}
-#endif
+#endif /* CONFIG_SMP */
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
Index: linux-2.6/kernel/sched/idle_task.c
===================================================================
--- linux-2.6.orig/kernel/sched/idle_task.c
+++ linux-2.6/kernel/sched/idle_task.c
@@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
-
-static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
-{
-	idle_exit_fair(rq);
-	rq_last_tick_reset(rq);
-}
-
-static void post_schedule_idle(struct rq *rq)
-{
-	idle_enter_fair(rq);
-}
 #endif /* CONFIG_SMP */
+
 /*
  * Idle tasks are unconditionally rescheduled:
  */
@@ -37,8 +27,7 @@ static struct task_struct *pick_next_tas
 {
 	schedstat_inc(rq, sched_goidle);
 #ifdef CONFIG_SMP
-	/* Trigger the post schedule to do an idle_enter for CFS */
-	rq->post_schedule = 1;
+	idle_enter_fair(rq);
 #endif
 	return rq->idle;
 }
@@ -58,6 +47,10 @@ dequeue_task_idle(struct rq *rq, struct
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+#ifdef CONFIG_SMP
+	idle_exit_fair(rq);
+	rq_last_tick_reset(rq);
+#endif
 }
 
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
@@ -101,8 +94,6 @@ const struct sched_class idle_sched_clas
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-	.pre_schedule		= pre_schedule_idle,
-	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/